diff options
Diffstat (limited to '.venv/lib/python3.12/site-packages/pip/_vendor/pygments/util.py')
| -rw-r--r-- | .venv/lib/python3.12/site-packages/pip/_vendor/pygments/util.py | 324 |
1 files changed, 324 insertions, 0 deletions
diff --git a/.venv/lib/python3.12/site-packages/pip/_vendor/pygments/util.py b/.venv/lib/python3.12/site-packages/pip/_vendor/pygments/util.py new file mode 100644 index 00000000..83cf1049 --- /dev/null +++ b/.venv/lib/python3.12/site-packages/pip/_vendor/pygments/util.py @@ -0,0 +1,324 @@ +""" + pygments.util + ~~~~~~~~~~~~~ + + Utility functions. + + :copyright: Copyright 2006-2024 by the Pygments team, see AUTHORS. + :license: BSD, see LICENSE for details. +""" + +import re +from io import TextIOWrapper + + +split_path_re = re.compile(r'[/\\ ]') +doctype_lookup_re = re.compile(r''' + <!DOCTYPE\s+( + [a-zA-Z_][a-zA-Z0-9]* + (?: \s+ # optional in HTML5 + [a-zA-Z_][a-zA-Z0-9]*\s+ + "[^"]*")? + ) + [^>]*> +''', re.DOTALL | re.MULTILINE | re.VERBOSE) +tag_re = re.compile(r'<(.+?)(\s.*?)?>.*?</.+?>', + re.IGNORECASE | re.DOTALL | re.MULTILINE) +xml_decl_re = re.compile(r'\s*<\?xml[^>]*\?>', re.I) + + +class ClassNotFound(ValueError): + """Raised if one of the lookup functions didn't find a matching class.""" + + +class OptionError(Exception): + """ + This exception will be raised by all option processing functions if + the type or value of the argument is not correct. + """ + +def get_choice_opt(options, optname, allowed, default=None, normcase=False): + """ + If the key `optname` from the dictionary is not in the sequence + `allowed`, raise an error, otherwise return it. + """ + string = options.get(optname, default) + if normcase: + string = string.lower() + if string not in allowed: + raise OptionError('Value for option {} must be one of {}'.format(optname, ', '.join(map(str, allowed)))) + return string + + +def get_bool_opt(options, optname, default=None): + """ + Intuitively, this is `options.get(optname, default)`, but restricted to + Boolean value. The Booleans can be represented as string, in order to accept + Boolean value from the command line arguments. If the key `optname` is + present in the dictionary `options` and is not associated with a Boolean, + raise an `OptionError`. If it is absent, `default` is returned instead. + + The valid string values for ``True`` are ``1``, ``yes``, ``true`` and + ``on``, the ones for ``False`` are ``0``, ``no``, ``false`` and ``off`` + (matched case-insensitively). + """ + string = options.get(optname, default) + if isinstance(string, bool): + return string + elif isinstance(string, int): + return bool(string) + elif not isinstance(string, str): + raise OptionError(f'Invalid type {string!r} for option {optname}; use ' + '1/0, yes/no, true/false, on/off') + elif string.lower() in ('1', 'yes', 'true', 'on'): + return True + elif string.lower() in ('0', 'no', 'false', 'off'): + return False + else: + raise OptionError(f'Invalid value {string!r} for option {optname}; use ' + '1/0, yes/no, true/false, on/off') + + +def get_int_opt(options, optname, default=None): + """As :func:`get_bool_opt`, but interpret the value as an integer.""" + string = options.get(optname, default) + try: + return int(string) + except TypeError: + raise OptionError(f'Invalid type {string!r} for option {optname}; you ' + 'must give an integer value') + except ValueError: + raise OptionError(f'Invalid value {string!r} for option {optname}; you ' + 'must give an integer value') + +def get_list_opt(options, optname, default=None): + """ + If the key `optname` from the dictionary `options` is a string, + split it at whitespace and return it. If it is already a list + or a tuple, it is returned as a list. + """ + val = options.get(optname, default) + if isinstance(val, str): + return val.split() + elif isinstance(val, (list, tuple)): + return list(val) + else: + raise OptionError(f'Invalid type {val!r} for option {optname}; you ' + 'must give a list value') + + +def docstring_headline(obj): + if not obj.__doc__: + return '' + res = [] + for line in obj.__doc__.strip().splitlines(): + if line.strip(): + res.append(" " + line.strip()) + else: + break + return ''.join(res).lstrip() + + +def make_analysator(f): + """Return a static text analyser function that returns float values.""" + def text_analyse(text): + try: + rv = f(text) + except Exception: + return 0.0 + if not rv: + return 0.0 + try: + return min(1.0, max(0.0, float(rv))) + except (ValueError, TypeError): + return 0.0 + text_analyse.__doc__ = f.__doc__ + return staticmethod(text_analyse) + + +def shebang_matches(text, regex): + r"""Check if the given regular expression matches the last part of the + shebang if one exists. + + >>> from pygments.util import shebang_matches + >>> shebang_matches('#!/usr/bin/env python', r'python(2\.\d)?') + True + >>> shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?') + True + >>> shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?') + False + >>> shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?') + False + >>> shebang_matches('#!/usr/bin/startsomethingwith python', + ... r'python(2\.\d)?') + True + + It also checks for common windows executable file extensions:: + + >>> shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?') + True + + Parameters (``'-f'`` or ``'--foo'`` are ignored so ``'perl'`` does + the same as ``'perl -e'``) + + Note that this method automatically searches the whole string (eg: + the regular expression is wrapped in ``'^$'``) + """ + index = text.find('\n') + if index >= 0: + first_line = text[:index].lower() + else: + first_line = text.lower() + if first_line.startswith('#!'): + try: + found = [x for x in split_path_re.split(first_line[2:].strip()) + if x and not x.startswith('-')][-1] + except IndexError: + return False + regex = re.compile(rf'^{regex}(\.(exe|cmd|bat|bin))?$', re.IGNORECASE) + if regex.search(found) is not None: + return True + return False + + +def doctype_matches(text, regex): + """Check if the doctype matches a regular expression (if present). + + Note that this method only checks the first part of a DOCTYPE. + eg: 'html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"' + """ + m = doctype_lookup_re.search(text) + if m is None: + return False + doctype = m.group(1) + return re.compile(regex, re.I).match(doctype.strip()) is not None + + +def html_doctype_matches(text): + """Check if the file looks like it has a html doctype.""" + return doctype_matches(text, r'html') + + +_looks_like_xml_cache = {} + + +def looks_like_xml(text): + """Check if a doctype exists or if we have some tags.""" + if xml_decl_re.match(text): + return True + key = hash(text) + try: + return _looks_like_xml_cache[key] + except KeyError: + m = doctype_lookup_re.search(text) + if m is not None: + return True + rv = tag_re.search(text[:1000]) is not None + _looks_like_xml_cache[key] = rv + return rv + + +def surrogatepair(c): + """Given a unicode character code with length greater than 16 bits, + return the two 16 bit surrogate pair. + """ + # From example D28 of: + # http://www.unicode.org/book/ch03.pdf + return (0xd7c0 + (c >> 10), (0xdc00 + (c & 0x3ff))) + + +def format_lines(var_name, seq, raw=False, indent_level=0): + """Formats a sequence of strings for output.""" + lines = [] + base_indent = ' ' * indent_level * 4 + inner_indent = ' ' * (indent_level + 1) * 4 + lines.append(base_indent + var_name + ' = (') + if raw: + # These should be preformatted reprs of, say, tuples. + for i in seq: + lines.append(inner_indent + i + ',') + else: + for i in seq: + # Force use of single quotes + r = repr(i + '"') + lines.append(inner_indent + r[:-2] + r[-1] + ',') + lines.append(base_indent + ')') + return '\n'.join(lines) + + +def duplicates_removed(it, already_seen=()): + """ + Returns a list with duplicates removed from the iterable `it`. + + Order is preserved. + """ + lst = [] + seen = set() + for i in it: + if i in seen or i in already_seen: + continue + lst.append(i) + seen.add(i) + return lst + + +class Future: + """Generic class to defer some work. + + Handled specially in RegexLexerMeta, to support regex string construction at + first use. + """ + def get(self): + raise NotImplementedError + + +def guess_decode(text): + """Decode *text* with guessed encoding. + + First try UTF-8; this should fail for non-UTF-8 encodings. + Then try the preferred locale encoding. + Fall back to latin-1, which always works. + """ + try: + text = text.decode('utf-8') + return text, 'utf-8' + except UnicodeDecodeError: + try: + import locale + prefencoding = locale.getpreferredencoding() + text = text.decode() + return text, prefencoding + except (UnicodeDecodeError, LookupError): + text = text.decode('latin1') + return text, 'latin1' + + +def guess_decode_from_terminal(text, term): + """Decode *text* coming from terminal *term*. + + First try the terminal encoding, if given. + Then try UTF-8. Then try the preferred locale encoding. + Fall back to latin-1, which always works. + """ + if getattr(term, 'encoding', None): + try: + text = text.decode(term.encoding) + except UnicodeDecodeError: + pass + else: + return text, term.encoding + return guess_decode(text) + + +def terminal_encoding(term): + """Return our best guess of encoding for the given *term*.""" + if getattr(term, 'encoding', None): + return term.encoding + import locale + return locale.getpreferredencoding() + + +class UnclosingTextIOWrapper(TextIOWrapper): + # Don't close underlying buffer on destruction. + def close(self): + self.flush() |